Learning to predict relapse in invasive ductal carcinomas based on the subcellular localization of junctional proteins.
ABSTRACT The complexity of breast cancer biology makes it challenging to analyze large datasets of clinicopathologic and molecular attributes, toward identifying the key prognostic features and producing systems capable of predicting which patients are likely to relapse. We applied machine-learning techniques to analyze a set of well-characterized primary breast cancers, which specified the abundance and localization of various junctional proteins. We hypothesized that disruption of junctional complexes would lead to the cytoplasmic/nuclear redistribution of the protein components and their potential interactions with growth-regulating molecules, which would promote relapse, and that machine-learning techniques could use the subcellular locations of these proteins, together with standard clinicopathological data, to produce an efficient prognostic classifier. We used immunohistochemistry to assess the expression and subcellular distribution of six junctional proteins, in addition to a panel of eight standard clinical features and concentrations of four "growth-regulating" proteins, to produce a database involving 36 features, over 66 primary invasive ductal breast carcinomas. A machine-learning system was applied to this clinicopathologic dataset to produce a decision-tree classifier that could predict whether a novel breast cancer patient would relapse. We show that this decision-tree classifier, which incorporates a combination of only four features (nuclear alpha- and beta-catenin levels, the total level of PTEN and the number of involved axillary lymph nodes), is able to correctly classify patient outcomes essentially 80% of the time. Further, this classifier is significantly better than classifiers based on any subgroup of these 36 features. This study demonstrates that autonomous machine-learning techniques are able to generate simple and efficient decision-tree prognostic classifiers from a wide variety of clinical, pathologic and biomarker data, and unlike other analytic methods, suggest testable biologic relationships among explicitly identified key variables. The decision-tree classifier resulting from these analytic methods is sufficiently simple and should be widely applicable to a spectrum of clinical cancer settings. Further, the subcellular distribution of junctional proteins, which influences growth regulatory pathways involved in locoregional and metastatic relapse of breast cancer, helped to identify which patients would relapse while their total concentration did not. This emphasizes the need to evaluate the subcellular distribution of junctional proteins in assessing their contribution to tumor progression.
- SourceAvailable from: download.bioon.com.cn[show abstract] [hide abstract]
ABSTRACT: The breast epithelium comprises cells at different stages of differentiation, including stem cells, progenitor cells, and more differentiated epithelial and myoepithelial cells. Wnt signaling plays a critical role in regulating stem/progenitor cells in the mammary gland as well as other tissue compartments. Furthermore, there is strong evidence suggesting that aberrant activation of Wnt signaling induces mammary tumors from stem/progenitor cells, and that Wnt exerts its oncogenic effects through LRP5/6-mediated activation of beta-catenin and mTOR pathways. Recent studies using avian retrovirus-mediated introduction of oncogenes into a small subset of somatic mammary cells suggest that polyoma middle T antigen (PyMT) may also preferentially transform stem/progenitor cells. These observations suggest that stem/progenitor cells in the mammary gland may be especially susceptible to oncogenic transformation. Whether more differentiated cells may also be transformed by particular oncogenes is actively debated; it is presently unclear whether stem cells or differentiated mammary cells are more susceptible to transformation by individual oncogenes. Better stem cell and progenitor cell markers as well as the ability to specifically target oncogenes into different mammary cell types will be needed to determine the spectrum of oncogene transformation for stem cells versus more differentiated cells.Stem Cell Reviews and Reports 07/2007; 3(2):157-68. · 4.52 Impact Factor
- [show abstract] [hide abstract]
ABSTRACT: Six genes confer a high risk for developing breast cancer (BRCA1/2, TP53, PTEN, STK11, CDH1). Both BRCA1 and BRCA2 have DNA repair functions, and BRCA1/2 deficient tumors are now being targeted by poly(ADP-ribose) polymerase inhibitors. Other genes conferring an increased risk for breast cancer include ATM, CHEK2, PALB2, BRIP1 and genome-wide association studies have identified lower penetrance alleles including FGFR2, a minor allele of which is associated with breast cancer. We review recent findings related to the function of some of these genes, and discuss how they can be targeted by various drugs. Gaining deeper insights in breast cancer susceptibility will improve our ability to identify those families at increased risk and permit the development of new and more specific therapeutic approaches.Human Genetics 09/2008; 124(1):31-42. · 4.63 Impact Factor
- [show abstract] [hide abstract]
ABSTRACT: In 1997, PTEN (phosphatase and tensin homologue deleted on chromosome 10, 10q23.3) was identified as an important tumor suppressor gene that is inactivated in a wide variety of human cancers. Ever since, PTEN's function has been extensively studied, and huge progress has been made in understanding PTEN's role in normal physiology and disease. In this review, we will systematically summarize the important data that have been gained from gene inactivation studies in mice and will put these data into physiological context using a tissue-by-tissue approach. We will cover mice exhibiting complete and constitutive inactivation of Pten as well as a large number of strains in which Pten has been conditionally deleted in specific tissues. We hope to highlight not only the tumor suppressive function of Pten but also its roles in embryogenesis and in the maintenance of the normal physiological functions of many organ systems.Oncogene 10/2008; 27(41):5398-415. · 7.36 Impact Factor